{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VK75VXRPZ6454OAKHTJUFMJWGW","short_pith_number":"pith:VK75VXRP","schema_version":"1.0","canonical_sha256":"aabfdade2fcfb9de380a3cd342b13635bb9e6b0a642bb0c44902044de1bd559c","source":{"kind":"arxiv","id":"2606.09351","version":1},"attestation_state":"computed","paper":{"title":"In-Context Learning for the Imputation of Public Opinion Data with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.CL","authors_text":"Anna-Carolina Haensch, Georg Ahnert, Joseph W Sakshaug, Tobias Holtdirk","submitted_at":"2026-06-08T11:25:10Z","abstract_excerpt":"Large language models have been widely evaluated as simulators of individual survey responses. In practice, however, fully unobserved responses are rare; the dominant problem is partial non-response. Imputation aims to restore the overall structure of a survey dataset by filling in these missing values. It has its own well-defined evaluation criteria and differs fundamentally from prediction. We propose to impute missing survey data through in-context learning (ICL). We systematically evaluate ICL design choices across different missingness mechanisms (MCAR, MAR, MNAR) on 150 opinion variables"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.09351","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T11:25:10Z","cross_cats_sorted":["stat.ME"],"title_canon_sha256":"0fcf52db8655967b47f77a9504fc74329a28a91ddf41e27b839fafc9c99ead52","abstract_canon_sha256":"d82175b97efd6540ac9ae9196e19a23fb25c2c7591f4f0761916db3db0e418c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:17.050015Z","signature_b64":"2XOnqi/JzNb1pp0PlMLSp9pe0RocaY4lcBcPFy37W+6MrrfzIGmwzGUk1DsYXwKHVwnsuTbLHIJkM5bTgjh2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aabfdade2fcfb9de380a3cd342b13635bb9e6b0a642bb0c44902044de1bd559c","last_reissued_at":"2026-06-09T02:08:17.049172Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:17.049172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Learning for the Imputation of Public Opinion Data with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME"],"primary_cat":"cs.CL","authors_text":"Anna-Carolina Haensch, Georg Ahnert, Joseph W Sakshaug, Tobias Holtdirk","submitted_at":"2026-06-08T11:25:10Z","abstract_excerpt":"Large language models have been widely evaluated as simulators of individual survey responses. In practice, however, fully unobserved responses are rare; the dominant problem is partial non-response. Imputation aims to restore the overall structure of a survey dataset by filling in these missing values. It has its own well-defined evaluation criteria and differs fundamentally from prediction. We propose to impute missing survey data through in-context learning (ICL). We systematically evaluate ICL design choices across different missingness mechanisms (MCAR, MAR, MNAR) on 150 opinion variables"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09351","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.09351/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.09351","created_at":"2026-06-09T02:08:17.049324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09351v1","created_at":"2026-06-09T02:08:17.049324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09351","created_at":"2026-06-09T02:08:17.049324+00:00"},{"alias_kind":"pith_short_12","alias_value":"VK75VXRPZ645","created_at":"2026-06-09T02:08:17.049324+00:00"},{"alias_kind":"pith_short_16","alias_value":"VK75VXRPZ6454OAK","created_at":"2026-06-09T02:08:17.049324+00:00"},{"alias_kind":"pith_short_8","alias_value":"VK75VXRP","created_at":"2026-06-09T02:08:17.049324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VK75VXRPZ6454OAKHTJUFMJWGW","json":"https://pith.science/pith/VK75VXRPZ6454OAKHTJUFMJWGW.json","graph_json":"https://pith.science/api/pith-number/VK75VXRPZ6454OAKHTJUFMJWGW/graph.json","events_json":"https://pith.science/api/pith-number/VK75VXRPZ6454OAKHTJUFMJWGW/events.json","paper":"https://pith.science/paper/VK75VXRP"},"agent_actions":{"view_html":"https://pith.science/pith/VK75VXRPZ6454OAKHTJUFMJWGW","download_json":"https://pith.science/pith/VK75VXRPZ6454OAKHTJUFMJWGW.json","view_paper":"https://pith.science/paper/VK75VXRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09351&json=true","fetch_graph":"https://pith.science/api/pith-number/VK75VXRPZ6454OAKHTJUFMJWGW/graph.json","fetch_events":"https://pith.science/api/pith-number/VK75VXRPZ6454OAKHTJUFMJWGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VK75VXRPZ6454OAKHTJUFMJWGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VK75VXRPZ6454OAKHTJUFMJWGW/action/storage_attestation","attest_author":"https://pith.science/pith/VK75VXRPZ6454OAKHTJUFMJWGW/action/author_attestation","sign_citation":"https://pith.science/pith/VK75VXRPZ6454OAKHTJUFMJWGW/action/citation_signature","submit_replication":"https://pith.science/pith/VK75VXRPZ6454OAKHTJUFMJWGW/action/replication_record"}},"created_at":"2026-06-09T02:08:17.049324+00:00","updated_at":"2026-06-09T02:08:17.049324+00:00"}